| train_ds: | |
| manifest_filepath: /manifests/combined_fisher_swbd_voxceleb12_librispeech/train.json | |
| sample_rate: 16000 | |
| labels: null | |
| batch_size: 64 | |
| shuffle: true | |
| time_length: 3 | |
| is_tarred: false | |
| tarred_audio_filepaths: null | |
| tarred_shard_strategy: scatter | |
| augmentor: | |
| noise: | |
| manifest_path: /manifests/noise/rir_noise_manifest.json | |
| prob: 0.5 | |
| min_snr_db: 0 | |
| max_snr_db: 15 | |
| speed: | |
| prob: 0.5 | |
| sr: 16000 | |
| resample_type: kaiser_fast | |
| min_speed_rate: 0.95 | |
| max_speed_rate: 1.05 | |
| num_workers: 15 | |
| pin_memory: true | |
| validation_ds: | |
| manifest_filepath: /manifests/combined_fisher_swbd_voxceleb12_librispeech/dev.json | |
| sample_rate: 16000 | |
| labels: null | |
| batch_size: 128 | |
| shuffle: false | |
| time_length: 3 | |
| num_workers: 15 | |
| pin_memory: true | |
| model_defaults: | |
| filters: 1024 | |
| repeat: 3 | |
| dropout: 0.1 | |
| separable: true | |
| se: true | |
| se_context_size: -1 | |
| kernel_size_factor: 1.0 | |
| enc_hidden: 640 | |
| pred_hidden: 640 | |
| joint_hidden: 640 | |
| preprocessor: | |
| _target_: nemo.collections.asr.modules.AudioToMelSpectrogramPreprocessor | |
| normalize: per_feature | |
| window_size: 0.025 | |
| sample_rate: 16000 | |
| window_stride: 0.01 | |
| window: hann | |
| features: 80 | |
| n_fft: 512 | |
| frame_splicing: 1 | |
| dither: 1.0e-05 | |
| spec_augment: | |
| _target_: nemo.collections.asr.modules.SpectrogramAugmentation | |
| freq_masks: 3 | |
| freq_width: 4 | |
| time_masks: 5 | |
| time_width: 0.03 | |
| encoder: | |
| _target_: nemo.collections.asr.modules.ConvASREncoder | |
| feat_in: 80 | |
| activation: relu | |
| conv_mask: true | |
| jasper: | |
| - filters: 1024 | |
| repeat: 1 | |
| kernel: | |
| - 3 | |
| stride: | |
| - 1 | |
| dilation: | |
| - 1 | |
| dropout: 0.0 | |
| residual: false | |
| separable: true | |
| se: true | |
| se_context_size: -1 | |
| - filters: 1024 | |
| repeat: 3 | |
| kernel: | |
| - 7 | |
| stride: | |
| - 1 | |
| dilation: | |
| - 1 | |
| dropout: 0.1 | |
| residual: true | |
| separable: true | |
| se: true | |
| se_context_size: -1 | |
| - filters: 1024 | |
| repeat: 3 | |
| kernel: | |
| - 11 | |
| stride: | |
| - 1 | |
| dilation: | |
| - 1 | |
| dropout: 0.1 | |
| residual: true | |
| separable: true | |
| se: true | |
| se_context_size: -1 | |
| - filters: 1024 | |
| repeat: 3 | |
| kernel: | |
| - 15 | |
| stride: | |
| - 1 | |
| dilation: | |
| - 1 | |
| dropout: 0.1 | |
| residual: true | |
| separable: true | |
| se: true | |
| se_context_size: -1 | |
| - filters: 3072 | |
| repeat: 1 | |
| kernel: | |
| - 1 | |
| stride: | |
| - 1 | |
| dilation: | |
| - 1 | |
| dropout: 0.0 | |
| residual: false | |
| separable: true | |
| se: true | |
| se_context_size: -1 | |
| decoder: | |
| _target_: nemo.collections.asr.modules.SpeakerDecoder | |
| feat_in: 3072 | |
| num_classes: 16681 | |
| pool_mode: attention | |
| emb_sizes: 192 | |
| angular: true | |
| loss: | |
| scale: 30 | |
| margin: 0.2 | |
| optim: | |
| name: sgd | |
| lr: 0.08 | |
| weight_decay: 0.0002 | |
| sched: | |
| name: CosineAnnealing | |
| warmup_ratio: 0.1 | |
| min_lr: 0.0 | |
| momentum: 0.9 | |
| target: nemo.collections.asr.models.label_models.EncDecSpeakerLabelModel | |